# Tool-calling on BFCL Extended Setting Source: [Tool-calling on BFCL Extended Setting]() Collection index: [llms.txt]() Data updated: 2026-03-13T07:58:19.772Z Evaluation of Tool-calling performance on the BFCL Extended Setting dataset, measured by Live, Non-Live, and Overall metrics. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Tool-calling | | Dataset (including any stated split) | BFCL Extended Setting | | Metric | Non-Live Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Non-Live Score](): Higher is better; unit: PERCENT. - [Live Score](): Higher is better; unit: PERCENT. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Non-Live Score | Result date | Report paper | | --- | --- | --- | --- | | GT\_Funs | 85.81 | Not recorded | 69b399ee0636e5bf4afbc92c | | Tool-DC (TF) | 84.4 | Not recorded | 69b399ee0636e5bf4afbc92c | | GT\_Funs | 79.23 | Not recorded | 69b399ee0636e5bf4afbc92c | | HiTEC-ICL | 76.81 | Not recorded | 69b399ee0636e5bf4afbc92c | | ToolGT (Prompting) | 76 | Not recorded | 69b399ee0636e5bf4afbc92c | | All\_Funs | 75.71 | Not recorded | 69b399ee0636e5bf4afbc92c | | Tool-DC (TF) | 71.79 | Not recorded | 69b399ee0636e5bf4afbc92c | | GT\_Funs | 70.96 | Not recorded | 69b399ee0636e5bf4afbc92c | | Top-K | 70.23 | Not recorded | 69b399ee0636e5bf4afbc92c | | Tool-DC (TF) | 64.13 | Not recorded | 69b399ee0636e5bf4afbc92c | | HiTEC-ICL | 63.79 | Not recorded | 69b399ee0636e5bf4afbc92c | | Top-K | 63.73 | Not recorded | 69b399ee0636e5bf4afbc92c | | All\_Funs | 62.73 | Not recorded | 69b399ee0636e5bf4afbc92c | | Top-K | 60.31 | Not recorded | 69b399ee0636e5bf4afbc92c | | ToolGT (Prompting) | 59.29 | Not recorded | 69b399ee0636e5bf4afbc92c | | HiTEC-ICL | 46.46 | Not recorded | 69b399ee0636e5bf4afbc92c | | All\_Funs | 40.69 | Not recorded | 69b399ee0636e5bf4afbc92c | | ToolGT (Prompting) | 39.58 | Not recorded | 69b399ee0636e5bf4afbc92c | ### GT\_Funs Non-Live Score: 85.81. Result ID: 69b3c2b947f34ce9249d91ba. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Tool-DC (TF) Non-Live Score: 84.4. Result ID: 69b3c2b947f34ce9249d91bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### GT\_Funs Non-Live Score: 79.23. Result ID: 69b3c2b947f34ce9249d91b4. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### HiTEC-ICL Non-Live Score: 76.81. Result ID: 69b3c2b947f34ce9249d91bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### ToolGT (Prompting) Non-Live Score: 76. Result ID: 69b3c2b947f34ce9249d91be. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### All\_Funs Non-Live Score: 75.71. Result ID: 69b3c2b947f34ce9249d91bb. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Tool-DC (TF) Non-Live Score: 71.79. Result ID: 69b3c2b947f34ce9249d91b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### GT\_Funs Non-Live Score: 70.96. Result ID: 69b3c2b947f34ce9249d91ae. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### Top-K Non-Live Score: 70.23. Result ID: 69b3c2b947f34ce9249d91bc. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Tool-DC (TF) Non-Live Score: 64.13. Result ID: 69b3c2b947f34ce9249d91b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### HiTEC-ICL Non-Live Score: 63.79. Result ID: 69b3c2b947f34ce9249d91b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Top-K Non-Live Score: 63.73. Result ID: 69b3c2b947f34ce9249d91b6. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### All\_Funs Non-Live Score: 62.73. Result ID: 69b3c2b947f34ce9249d91b5. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### Top-K Non-Live Score: 60.31. Result ID: 69b3c2b947f34ce9249d91b0. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### ToolGT (Prompting) Non-Live Score: 59.29. Result ID: 69b3c2b947f34ce9249d91b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-3B-Instruct"}. This record does not assert independent reproduction. ### HiTEC-ICL Non-Live Score: 46.46. Result ID: 69b3c2b947f34ce9249d91b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### All\_Funs Non-Live Score: 40.69. Result ID: 69b3c2b947f34ce9249d91af. [Reporting paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### ToolGT (Prompting) Non-Live Score: 39.58. Result ID: 69b3c2b947f34ce9249d91b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Scale":"Qwen2.5-1.5B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.